Black Box Adversarial Prompting for Foundation Models
Keywords:
Generative Models
black-box optimization
large language models
text-to-text
foundation models
Adversarial Attacks
applications of bayesian optimization
text-to-image
prompting
Abstract
Prompting interfaces allow users to quickly adjust the output of generative models in both vision and language. However, small changes and design choices in the prompt can lead to significant differences in the output. In this work, we develop a black-box framework for generating adversarial prompts for unstructured image and text generation. These prompts, which can be standalone or prepended to benign prompts, induce specific behaviors into the generative process, such as generating images of a particular object or generating high perplexity text.
Video
Chat is not available.
Successful Page Load